9188 papers
The paper introduces SEED, a novel semantic evaluation metric for visual brain decoding that integrates three neuroscientifically inspired components to achieve superior alignment with human judgments, revealing critical limitations in current state-of-the-art models and providing open-source data to guide future advancements.
VisionLogic is a novel neural-symbolic framework that generates faithful, hierarchical explanations for vision models by learning activation thresholds to form predicates, inducing class-level logical rules, and grounding these rules in causally validated visual concepts through ablation-based testing.
This paper introduces ELogitNorm, a novel hyperparameter-free training method that addresses feature collapse in Logit Normalization by adding a feature distance-awareness loss term, thereby significantly improving out-of-distribution detection and in-distribution confidence calibration without compromising classification accuracy.
This paper proposes an efficient LiDAR-camera fusion framework featuring a UniMT detector and an RTMCT predictor that achieves state-of-the-art 3D object detection and trajectory prediction performance while enabling real-time inference on resource-constrained service robots.
This paper reproduces the CheXNet algorithm and explores improved deep learning models on the NIH ChestX-ray14 dataset, achieving an average AUC-ROC of 0.85 and an average F1 score of 0.39 across 14 disease classifications.
This paper introduces HoloLLM, a multimodal foundation model that integrates diverse sensing modalities like LiDAR and mmWave radar through a novel Universal Modality-Injection Projector and a collaborative data curation pipeline to significantly enhance language-grounded human perception and reasoning in real-world embodied agents.
This paper proposes a training-time transform coding method that integrates a hierarchical analysis-synthesis transform—combining channel-wise KLT and a sparsity-aware neural transform—with 3D Gaussian Splatting representation and entropy modeling to significantly improve rate-distortion performance while maintaining fast decoding speeds.
This paper presents SpikePingpong, a novel robotic table tennis system that integrates a Fast-Slow architecture combining spike-based vision for rapid trajectory prediction with imitation learning for precise motion planning, achieving high-precision ball striking in dynamic environments.
This paper introduces Adaptive Low-Pass Guidance (ALG), a training-free method that enhances motion dynamics in image-to-video generation by filtering high-frequency details from the conditioning image during early denoising stages, thereby preventing the model from overfitting to static appearances while preserving image quality and text alignment.
This paper introduces UPNet, a lightweight feedforward network that predicts neural uncertainty maps from single images to efficiently select the most informative viewpoints for 3D reconstruction, achieving comparable accuracy to existing methods with significantly reduced computational costs and superior generalization to novel object categories.
This paper addresses the lack of representative faulty data for training AI-based fault detection in Vision-Based Navigation by systematically characterizing camera sensor faults and introducing a simulation framework to generate a comprehensive dataset of fault-injected images for interplanetary exploration missions.
This paper proposes NRSeg, a noise-resilient learning framework that leverages synthetic data from driving world models for Birds' Eye View semantic segmentation by introducing a Perspective-Geometry Consistency Metric, a Bi-Distribution Parallel Prediction mechanism for uncertainty quantification, and a Hierarchical Local Semantic Exclusion module, thereby achieving state-of-the-art performance in unsupervised and semi-supervised tasks.
This paper presents SFATTI, an FPGA-based spiking neural network accelerator generated via the open-source Spiker+ framework, demonstrating its effectiveness for low-latency, energy-efficient handwritten digit recognition on the MNIST dataset within edge computing constraints.
This paper presents the first closed-loop control system enabling a quadrotor to hover and maneuver stably within narrow pipes by utilizing a low-latency, event-based smoke velocimetry method to estimate real-time airflow disturbances, which are then processed by a recurrent neural network and integrated into a reinforcement learning-based controller to effectively counteract aerodynamic effects and prevent wall collisions.
FedGIN is a federated learning framework that addresses data scarcity, domain shift, and privacy concerns in multi-modal medical imaging by integrating a lightweight Global Intensity Non-linear (GIN) augmentation module to significantly improve cross-modality organ segmentation performance without sharing raw patient data.
This paper proposes a novel Noise-Suppression Feature Pyramid Network (NS-FPN) that integrates Low-frequency guided Feature Purification and Spiral-aware Feature Sampling modules to address the false alarm problem in Infrared Small Target Detection and Segmentation by suppressing noise from a frequency domain perspective.
This paper proposes Single-Step Diffusion Regularization (SSD-Reg), a physics-informed hybrid framework that integrates diffusion models as learned regularization within a variational scheme to reconstruct high-quality microwave tomography images without requiring paired training data.
This paper proposes TS-Mamba, a novel online video super-resolution method that leverages trajectory-aware token selection and shifted State Space Models to achieve state-of-the-art performance with significantly reduced computational complexity by effectively modeling long-range temporal dependencies and spatial continuity.
MoSA is a novel framework that decouples human video generation into structure and appearance components, utilizing a 3D structure transformer and specialized constraints to achieve superior motion coherence and realistic human-environment interactions compared to existing models.
This paper proposes DeReF, a novel multimodal framework for cancer survival prediction that addresses limitations in existing fusion methods by introducing a random feature reorganization strategy between modality decoupling and dynamic Mixture-of-Experts fusion to enhance feature diversity and inter-modal information interaction.